Parameterization of state duration in Hidden semi-Markov Models: an application in electrocardiography
This work addresses the challenge of learning from limited data in electrocardiography, but it is incremental as it builds on existing Hidden semi-Markov Models with a focus on duration parameterization.
The authors tackled the problem of time series classification from a single example by introducing a parametric Hidden semi-Markov Model with variable state durations, and they applied it to heartbeat classification to compare discrete and Gamma distribution representations.
This work aims at providing a new model for time series classification based on learning from just one example. We assume that time series can be well characterized as a parametric random process, a sort of Hidden semi-Markov Model representing a sequence of regression models with variable duration. We introduce a parametric stochastic model for time series pattern recognition and provide a maximum-likelihood estimation of its parameters. Particularly, we are interested in examining two different representations for state duration: i) a discrete density distribution requiring an estimate for each possible duration; and ii) a parametric family of continuous density functions, here the Gamma distribution, with just two parameters to estimate. An application on heartbeat classification reveals the main strengths and weaknesses of each alternative.